© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76981
    Prev
    Next
    INDEX
    Explanations

    truth, victims, reconciliation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atürk
    -0.81
     δ
    -0.81
     нах
    -0.76
    delete
    -0.74
    Château
    -0.73
     Син
    -0.73
     influencer
    -0.73
    ofluor
    -0.71
     corrections
    -0.71
     دولار
    -0.70
    POSITIVE LOGITS
     truth
    1.35
     Truth
    1.27
     victims
    1.22
    Truth
    1.14
     Victims
    1.08
     victim
    1.02
     Repar
    1.01
     survivors
    0.96
     TRUTH
    0.94
    truth
    0.93
    Activations Density 0.026%

    No Known Activations